Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 576 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0853. Min Range: -8.0853
Max Act: 8.0853. Min Act: -0.1700
Data Index: 7375030 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0853. Min Range: -8.0853
Max Act: 8.0228. Min Act: -0.1700
Data Index: 5074756 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0853. Min Range: -8.0853
Max Act: 7.9603. Min Act: -0.1700
Data Index: 5074755 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0853. Min Range: -8.0853
Max Act: 7.9603. Min Act: -0.1700
Data Index: 6235910 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0853. Min Range: -8.0853
Max Act: 7.8353. Min Act: -0.1700
Data Index: 565013 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0853. Min Range: -8.0853
Max Act: 7.7415. Min Act: -0.1700
Data Index: 6476060 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0853. Min Range: -8.0853
Max Act: 7.6165. Min Act: -0.1700
Data Index: 6476061 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0853. Min Range: -8.0853
Max Act: 7.5853. Min Act: -0.1700
Data Index: 4620715 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0853. Min Range: -8.0853
Max Act: 7.5853. Min Act: -0.1700
Data Index: 540570 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0853. Min Range: -8.0853
Max Act: 7.5540. Min Act: -0.1700
Data Index: 6676533 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0853. Min Range: -8.0853
Max Act: 7.5228. Min Act: -0.1700
Data Index: 7294971 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0853. Min Range: -8.0853
Max Act: 7.4915. Min Act: -0.1700
Data Index: 297498 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0853. Min Range: -8.0853
Max Act: 7.4290. Min Act: -0.1700
Data Index: 1173470 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0853. Min Range: -8.0853
Max Act: 7.3978. Min Act: -0.1700
Data Index: 8069143 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0853. Min Range: -8.0853
Max Act: 7.3978. Min Act: -0.1700
Data Index: 4824680 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0853. Min Range: -8.0853
Max Act: 7.3665. Min Act: -0.1700
Data Index: 3196711 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0853. Min Range: -8.0853
Max Act: 7.3040. Min Act: -0.1700
Data Index: 5762590 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0853. Min Range: -8.0853
Max Act: 7.3040. Min Act: -0.1700
Data Index: 2772641 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0853. Min Range: -8.0853
Max Act: 7.2728. Min Act: -0.1700
Data Index: 2934052 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0853. Min Range: -8.0853
Max Act: 7.2415. Min Act: -0.1700
Data Index: 5242201 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19